M3-Med is a new bilingual benchmark that tests video-language AI models on multi-hop temporal reasoning in medical instructional videos, and it shows a large gap between current models and human performance.
19 Zhen Yao, Jiawei Xu, Shuhang Hou, and Mooi Choo Chuah
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
M$^3$-Med: A Benchmark for Multi-lingual, Multi-modal, and Multi-hop Reasoning in Medical Instructional Video Understanding
M3-Med is a new bilingual benchmark that tests video-language AI models on multi-hop temporal reasoning in medical instructional videos, and it shows a large gap between current models and human performance.